© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10997
    Prev
    Next
    INDEX
    Explanations

    requirements and needs

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric expressions—digits and quantities (e.g. rates, measurements, percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $
    -1.81
     different
    -1.53
    )
    -1.48
    и
    -1.40
     különböző
    -1.39
    id
    -1.39
    They
    -1.38
     verschiedene
    -1.38
     役
    -1.38
    }
    -1.38
    POSITIVE LOGITS
     kancel
    1.48
     and
    1.47
    เกง
    1.38
     if
    1.38
    Steg
    1.35
    ญี่ป
    1.33
    🅘
    1.31
    seks
    1.30
     ако
    1.30
     zakon
    1.30
    Activations Density 0.046%

    No Known Activations